OR-Parallel Execution of Prolog on BC-Machine

We present the principles of OR-parallel execution of Prolog on a special parallel inference machine, named BC-machine. The machine is a combined local and shared memory multiprocessor with a special interconnection network. The network allows write operations of an active processor to be broadcasted to several idle processors simultaneously. The shared memory is mainly used for sharing some control information among processors in the system. The amount of shared control information is small and accessed relatively seldom. The execution model is based on the local address space approach. It allows all the technology developed for standard Prolog to be used without loss of efficiency. We expect that the model substantially reduces the copying overhead in comparision with all previous related models. This reduction is due to our new idea of dynamic load balancing and the broadcast mechanism supported by the network. A prototype system of 9 processors is under construction at the Swedish Institute of Computer Science in Stockholm.